Structure-SLAM: Low-Drift Monocular SLAM in Indoor Environments
This addresses drift issues in indoor SLAM for robotics and AR applications, but it is incremental as it builds on existing monocular SLAM techniques with specific improvements.
The paper tackles the problem of monocular SLAM failing in indoor environments due to lack of textured surfaces by proposing a method that decouples rotation and translation estimation, using surface normals from a CNN and spherical mean-shift clustering, resulting in outperforming state-of-the-art on benchmarks like ICL-NUIM and TUM RGB-D.
In this paper a low-drift monocular SLAM method is proposed targeting indoor scenarios, where monocular SLAM often fails due to the lack of textured surfaces. Our approach decouples rotation and translation estimation of the tracking process to reduce the long-term drift in indoor environments. In order to take full advantage of the available geometric information in the scene, surface normals are predicted by a convolutional neural network from each input RGB image in real-time. First, a drift-free rotation is estimated based on lines and surface normals using spherical mean-shift clustering, leveraging the weak Manhattan World assumption. Then translation is computed from point and line features. Finally, the estimated poses are refined with a map-to-frame optimization strategy. The proposed method outperforms the state of the art on common SLAM benchmarks such as ICL-NUIM and TUM RGB-D.